Marine Disasters Research Articles

Human Adaption to Climate Change: Marine Disaster Risk Reduction in the Era of Intelligence

With the intensification of global warming and sea level rise, extreme weather and climate events occur frequently, increasing the probability and destructive power of marine disasters. The purpose of this paper is to propose the specific application of artificial intelligence (AI) in marine disaster risk reduction. First, this paper uses computer vision to assess the vulnerability of the target and then uses CNN-LSTM to forecast tropical cyclones. Second, this paper proposes a social media communication mechanism based on deep learning and a psychological crisis intervention mechanism based on AIGC. In addition, the rescue response system based on an intelligent unmanned platform is also the focus of this research. Third, this paper also attempts to discuss disaster loss assessment and reconstruction based on machine learning and smart city concepts. After proposing specific application measures, this paper proposes three policy recommendations. The first one is improving legislation to break the technological trap of AI. The second one is promoting scientific and technological innovation to break through key technologies of AI. The third one is strengthening coordination and cooperation to build a disaster reduction system that integrates man and machine. The purpose of this paper is to reduce the risk of marine disasters by applying AI. Furthermore, we hope to provide scientific references for sustainability and human adaptation to climate change.

How to encourage more public participation in marine disaster risk management: Evidence from a survey experiment in China

Raising public awareness of maritime risk and disseminating information about disaster prevention and reduction are the most frequent ways that the government incorporates citizens in marine disaster risk management (DRM). However, these measures are deemed to be insufficient to drive the participation rate. This study aims to understand the participation trend of citizens in marine DRM. On the basis of the theory of citizen participation’s ladder, public participation within marine DRM is categorized into non-participation, tokenistic participation, and substantive participation. Using organization theory, the government’s strategies for encouraging participation are classified into common approach (raising awareness), structural approach (innovating instruments), and cultural approach (developing citizenship). Considering the vignette experiment of 403 citizens in a coastal city of China that has historically been subject to marine disasters, it was found that effectiveness of the strategies, from highest to lowest, are citizenship development, risk education, and instruments innovation. At the individual level, psychological characteristics such as trust in the government, past disaster experience, and knowledge of marine DRM did not significantly influence citizens’ participation preferences. At the government level, even when citizens are informed about new participatory mechanisms and tools, they still tend to be unwilling to share responsibilities. However, self-efficacy and understanding the beneficial outcomes of their participation in marine (DRM) can positively impact the willingness to participate. The results show that to encourage public participation substantively in the marine DRM, it is important to cultivate a sense of civic duty and enhance citizens’ sense of ownership, fostering a closer and more equitable partnership between the state and society.

The Affordable Virtual Learning Technology of Sea Salt Farming across Multigenerational Users through Improving Fitts’ Law

Sea salt farms are the source of salt, an indispensable essential ingredient in various foods and products. Further, they act as frontlines to protect marine disasters from entering domestic residential areas. However, sea salt farming has decreased in popularity among recent-generation farmers in Samut Songkhram Province, Thailand. This paper presents the development of an affordable virtual learning (AVL) application for Thailand’s sea salt farming. Fitts’ law was applied to optimize user-interactive objects’ size and placement to reduce selection time. The sample consisted of 127 multigenerational users, namely those in Generation X, Generation Y, and Generation Z. This study found that the developed AVL applied Fitts’ law to be used harmoniously with VR economical equipment. A total of 90.55% of multigenerational users were satisfied with the developed AVL. The “Looking” and “Executing by eye focus” activities were enjoyed by 100% of participants. The following activities were “Walking” and “Listening”, with 82.68% and 77.95% enjoying them, respectively. Generation Z users responded more to the “Walking” activity than Generation X and Y users. In addition, the hypothesis testing result of learning outcomes through AVL was consistent among multigenerational users. Therefore, the developed AVL should be used as a medium to conserve sea salt farming in Thailand.

Zirconium-based metal-organic framework composites for solid phase extraction of brevetoxin-A from seawater

Red tides are a type of natural marine disaster caused by harmful algae characterized by a high toxicity, wide distribution, and long duration. Since the concentration of algal toxins in seawater increases with the occurrence of red tides, algal toxins detected in seawater could be used to predict the occurrence and evolution of red tides. Brevetoxin-A (BTX-A) is a secondary metabolite produced by the harmful algae Karenia brevis, whose detection in seawater could form the basis of an accurate warning system for incoming red tides. However, due to the inherent complexity of the seawater matrix and the extremely low levels of BTX-A in seawater, the use of instruments for its direct detection is difficult. Therefore, there is an urgent need to develop a sample pretreatment method for the efficient enrichment of BTX-A in seawater. In this study, a metal-organic backbone material (UiO-66) and its composite with silica microspheres (SiO2@UiO-66) were successfully synthesized using the solvothermal method. The prepared SiO2@UiO-66 exhibited good hydrophilicity, water stability, and large specific surface area. Furthermore, it also exhibited hydrogen bonding and electrostatic interactions with BTX-A, had a strong affinity for BTX-A, and was able to efficiently adsorb BTX-A in complex matrices. Therefore, SiO2@UiO-66 showed potential as a novel packing material for the extraction of BTX-A from solid phase extraction columns. Combined with high performance liquid chromatography-tandem mass spectrometry (HPLC-MS/MS), a highly sensitive detection method for the determination of BTX-A in marine water was established. The established analytical method had a low detection limit (3.0 pg/mL), a wide linear range (10.0 -200.0 pg/mL), and a good linear relationship (R=0.9992). Combined with the Fujian Province Red Tide Monitoring and Early Warning Information 2021 issued by the Fujian Provincial Oceanic and Fisheries Bureau, the analytical method established herein was successfully applied to analyze and monitor the content of BTX-A in actual seawater samples. This highlights the proposed system's potential for use as an early warning factor in the monitoring of red tides, representing a simple and fast pretreatment methodology for the detection of BTX-A in seawater.

Typical Marine Ecological Disasters in China Attributed to Marine Organisms and Their Significant Insights.

Owing to global climate change or the ever-more frequent human activities in the offshore areas, it is highly probable that an imbalance in the offshore ecosystem has been induced. However, the importance of maintaining and protecting marine ecosystems' balance cannot be overstated. In recent years, various marine disasters have occurred frequently, such as harmful algal blooms (green tides and red tides), storm surge disasters, wave disasters, sea ice disasters, and tsunami disasters. Additionally, overpopulation of certain marine organisms (particularly marine faunas) has led to marine disasters, threatening both marine ecosystems and human safety. The marine ecological disaster monitoring system in China primarily focuses on monitoring and controlling the outbreak of green tides (mainly caused by outbreaks of some Ulva species) and red tides (mainly caused by outbreaks of some diatom and dinoflagellate species). Currently, there are outbreaks of Cnidaria (Hydrozoa and Scyphozoa organisms; outbreak species are frequently referred to as jellyfish), Annelida (Urechis unicinctus Drasche, 1880), Mollusca (Philine kinglipini S. Tchang, 1934), Arthropoda (Acetes chinensis Hansen, 1919), and Echinodermata (Asteroidea organisms, Ophiuroidea organisms, and Acaudina molpadioides Semper, 1867) in China. They not only cause significant damage to marine fisheries, tourism, coastal industries, and ship navigation but also have profound impacts on marine ecosystems, especially near nuclear power plants, sea bathing beaches, and infrastructures, posing threats to human lives. Therefore, this review provides a detailed introduction to the marine organisms (especially marine fauna species) causing marine biological disasters in China, the current outbreak situations, and the biological backgrounds of these outbreaks. This review also provides an analysis of the causes of these outbreaks. Furthermore, it presents future prospects for marine biological disasters, proposing corresponding measures and advocating for enhanced resource utilization and fundamental research. It is recommended that future efforts focus on improving the monitoring of marine biological disasters and integrating them into the marine ecological disaster monitoring system. The aim of this review is to offer reference information and constructive suggestions for enhancing future monitoring, early warning systems, and prevention efforts related to marine ecological disasters in support of the healthy development and stable operation of marine ecosystems.

Multi-technique analysis of seawater impact on the performance of calcium sulphoaluminate cement mortar

The construction of offshore islands and reefs requires the development of new seawater sea-sand concrete materials. This study investigated the impact of seawater on the performance of calcium sulphoaluminate (CSA) cement mortar, with mechanism analyses by the acoustic emission (AE) and digital image correlation (DIC). For all uniaxial compression tests, cumulated AE, average AE frequency, rise angle, b-value, and βt coefficient were considered to perform the failure analysis. In addition, other techniques such as X-ray diffraction (XRD), scanning electron microscopy (SEM), and energy dispersive spectroscopy (EDS) were also employed to highlight the effects of seawater on the hydration products and microstructure of the CSA cement. The results show that seawater not only promotes the formation and growth of ettringite (AFt) but also interacts with cement hydration products to produce Friedel’s salt and various gel formations. Compared to freshwater mixing (0 %), using seawater mixing at normal concentrations (3.3 %) enhances the compactness of the CSA cement, thereby improving the strength and ductility of the CSA mortar. Specifically, the peak load increases from 77 kN to about 86 kN when mixed with seawater at normal concentration, whereas higher seawater concentrations (6.6 %, 9.9 %) resulted in a slight decrease in strength of the CSA mortar, with the peak load reaching approximately 80 kN, yet the ductility is enhanced, as evidenced by the softening post-peak branch of the loading curve. Additionally, AE bursts have a strong correlation with the fracture of the CSA mortar, which can also be forecast by the AE time-scaling coefficient βt. Therefore, when constructing oceanic island and reef foundations, this type of seawater sea-sand concrete is preferred due to its improved ductility and strength, which enhances the structural integrity of marine constructions and provides early warning for effective marine disaster prediction.

Effects of tropical cyclone intensity on spatial footprints of storm surges: an idealized numerical experiment

Abstract Storm surges caused by tropical cyclones (TCs) have long ranked first among all types of marine disasters in casualties and economic losses, and can lead to further regional exacerbation of consequences stemming from these losses along different coastlines. Understanding the spatial footprints of storm surges is thus highly important for developing effective risk management and protection plans. To this end, we designed an ideal storm surge model based on FVCOM to explore the relationship between TC intensity and the spatial footprint of storm surges, and its intrinsic mechanism. The spatial footprints of both positive and negative storm surges were positively correlated with TC intensity; however, the latter was more sensitive to the intensity when the TC intensity is weaker than CAT3 TC’s. The average positive storm surge footprint of CAT1 was 574 km, with CAT3 and CAT5 increasing by 6% and 25%, respectively, compared to CAT1. The average spatial footprint of the negative storm surge of CAT1 was 1,407 km, with CAT3 and CAT5 increasing by 18% and 29%, respectively, compared to CAT1. The decomposition and mechanism analysis of the storm surge show that the main contributing component of the total surge at the south end of the storm’s landfall and during the time of the forerunner was the Ekman surge, whereas the contribution of the normal surge component to the north and during the time of the main surge and resurgence was dominant. In addition, not all the spatial footprints of the storm surge components increased with the TC intensity, as the total surge did, similar to the Ekman surge. These quantitative analyses and intrinsic mechanisms provide a theoretical basis for predicting and evaluating storm surge risks.

Hazard assessment of dynamic marine processes during two extreme weather systems near the Shandong Peninsula

Typhoons and extratropical cyclones both occurred frequently on the Shandong Peninsula and have induced severe dynamic marine disasters. In this study, the typhoons and extratropical cyclones that occurred from 1979 to 2018 were counted and classified according to their tracks. We simulated the storm surge and disastrous waves using a coupled ocean-wave model and assessed the hazard distribution under different types of typhoons and extratropical cyclones. Through comparison, it was found that the southern Yellow Sea steering type typhoons and Yangtze-Huai cyclones occurred most frequently and were most likely to cause disasters. Regarding the hazard posed by the storm surge, there was a clear demarcation between the northern and southern coasts of the peninsula, as well as between the eastern and western coasts. The western coast of the peninsula was more exposed to storm surges induced by typhoons, while the northern coast of the peninsula was more exposed to storm surges induced by extratropical cyclones. The hazard posed by waves exhibited a localized characteristic. The wave hazard was the greatest near the peninsula cape and the lowest surrounding the Laizhou Bay, which was contrary to the distribution of the storm surge hazard. The identification of key management areas for disasters provides basic data and a technical reference for coastal development planning and can play a positive role in disaster prevention.

Cooperative task allocation method for air-sea heterogeneous unmanned system with an application to ocean environment information monitoring

Ocean environment information monitoring is crucial to maritime battlefield situation awareness, marine disaster prevention, and marine resources utilization. However, current monitoring means, including remote sensing satellites, scientific investigation ships, and ocean observation stations, have limitations in terms of spatial coverage, spatiotemporal resolution, and manpower resources. Therefore, this study proposed the Air-Sea heterogeneous unmanned system composed of UAVs and USVs to carry out ocean environment information monitoring tasks.) Firstly, an algorithm named FASO (Firefly Algorithm Based Particle Swarm Optimization) is proposed to obtain the deployment of monitoring nodes in the sea-surface and airspace. Secondly, a multi-objective optimization cooperative task allocation model is established, which contains complex constraints and takes the energy consumption cost of UAVs and USVs as optimization goals. Finally, a cooperative task allocation method based on the improved NSGA-II algorithm is presented to enhance the convergence speed and quality of the cooperative task allocation for air-sea heterogeneous unmanned system. Simulation results demonstrate that the proposed algorithm have higher generality and superiority compared to other algorithms. This study provides a specific approach for the application of heterogeneous unmanned systems in the field of ocean monitoring.

Double-Swing Spring Origami Triboelectric Nanogenerators for Self-Powered Ocean Monitoring

Coastal areas often experience high population density and intense human activity owing to the considerable value of the ocean. Therefore, devices for monitoring marine disasters are crucial for ensuring the safety of human life. Herein, we develop hemispherical spring origami (SO) triboelectric nanogenerators (TENGs) (HSO-TENGs) for self-powered ocean wave monitoring. Optimization is performed using two approaches. First, swing machine experiments are conducted to investigate the monitoring performance of the HSO-TENGs regarding wave height and period with satisfactory accuracy. To increase power generation and monitoring accuracy, the internal inertia and centroid of gravity of the HSO-TENGs are optimized with respect to the structural parameters (i.e., magnet weight, hammer height, and external swing arm length). Second, numerical simulations are performed using the smoothed-particle hydrodynamics (SPH) method to determine the most suitable fixed condition for the HSO-TENGs for sensing wave changes. Subsequently, wave tank experiments are conducted on the HSO-TENGs to determine their ability to sense wave height, period, frequency, and direction. Tests related to supplying other sensors are also conducted. Eventually, the ability of the HSO-TENGs to monitor wave direction and spreading parameters is investigated in a numerical SPH circular wave tank. The results prove that the optimized HSO-TENGs can achieve powering and sensing through the same device.

Effective attention model for global sea surface temperature prediction

Sea Surface Temperature (SST) is an essential parameter of the ocean–atmosphere system, so accurately predicting the future SST is of great significance. To address the low prediction accuracy due to insufficient consideration of spatiotemporal correlations in existing machine learning models, this paper proposes an Effective Attention Model (EAM) to achieve daily global SST prediction (predicting the SST of the next 15 days using those of the past 15 days) and monthly global SST prediction (predicting the SST of the next 12 months using those of the past 12 months). The EAM adopts an attention mechanism to avoid information redundancy and improve prediction accuracy. This is the first work to realize high-accuracy global SST prediction with a high spatial resolution of 0.25° on two time scales (daily and monthly) based on deep learning. Experiments show that (1) the prediction results have a consistent global spatiotemporal distribution with the ground truth, with the Root Mean Squared Difference (RMSD) of daily prediction ranging from 0.212 to 0.932 ℃ and the RMSD of monthly prediction ranging from 0.666 to 0.782 ℃. The EAM is superior to the deep learning models (ConvLSTM, 3D-CNN, and LSTM) and the numerical model (HYCOM); (2) Besides global prediction, the EAM also achieves good performance in a climate change sensitive area (Niño 3.4 sea area), with the lowest RMSD of 0.231 ℃. This study may not only benefit the research on climate events (El Niño and La Niña) but also serve to predict other marine disasters (such as heat waves and storms). In the future, the proposed attention module can also be adapted to other prediction scenarios such as meteorology.

Reconstruction of Wide Swath Significant Wave Height From Quasi‐Synchronous Observations of Multisource Satellite Sensors

AbstractGlobal sea wave monitoring is of utmost importance for tasks such as analysis of ocean climate change, offshore fisheries, and early warning of marine disasters. Significant wave height (SWH) is one of the most vital and widely used metrics for measuring sea waves in marine research. Hence, obtaining high precision and extensive coverage measurements of SWH is of great significance for comprehensive sea wave studies. A data set is constructed by combining wave spectrometer and scatterometer data from China‐French Ocean Satellite, synthetic aperture radar (SAR) wave mode data from Sentinel‐1, and altimeter data from Jason‐3 and HY‐2B through space‐time matching method. The multi‐sources integrated data set is used to complete the reconstruction of the wide swath SWH. A model based on stacked autoencoder and deep neural network (SAE‐DNN) is developed. The SWH reconstructed by the model is evaluated with the training‐independent test set. The results demonstrate that the accuracy of the SAE‐DNN model is significantly improved by incorporating SAR joint quasi‐synchronous observations and the root mean square error can reach 0.217 m, which is comparable to the SWH measured by altimeter and highlights the effectiveness and reliability of the model in accurately reconstructing SWH. We further examine and analysis the distance variations between SWH reconstruction sites and Surface Wave Investigation and Monitoring observations, the influence of different SAR features, and the influence of sea state, highlighting the benefits of incorporating SAR data into SAE‐DNN model.

A Node Deployment Method Based on Improved Snake Optimizer for Marine Disasters

A Node Deployment Method Based on Improved Snake Optimizer for Marine Disasters

Long-Term Spatiotemporal Characteristics of Ulva prolifera Green Tide and Effects of Environmental Drivers on Its Monitoring by Satellites: A Case Study in the Yellow Sea, China, from 2008 to 2023

Ulva prolifera (U. prolifera) green tide outbreaks have occurred in the Yellow Sea of China for many years, causing serious losses to marine ecology and the marine economy. The monitoring and tracking of U. prolifera green tide is a crucial aspect of marine ecological disaster prevention and control management. This paper aims to investigate the spatiotemporal distribution changes in U. prolifera green tide in the Yellow Sea throughout its life cycle. A survey of the Yellow Sea from 2008 to 2023 was conducted using multi-source remote sensing images. Long-term monitoring and analysis of U. prolifera revealed the evolution process of the green tide, including the early development, outbreak, decline, and extinction stages, considering time, space, and frequency of occurrence. Additionally, this study examined peak coverage change patterns over the past 16 years and analyzed the influence of environmental factors such as sea surface temperature and sea surface wind field on the development of U. prolifera. The research results serve as a valuable reference for the monitoring, early warning, and scientific prevention and control of U. prolifera green tide in the Yellow Sea, as well as other similar marine disaster areas.

Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution

Green tides are marine disasters caused by the explosive proliferation or high concentration of certain large algae in seawater, which causes discoloration of the water body. Accurate monitoring of its distribution area is highly important for early warning and the protection of marine ecology. However, existing deep learning methods have difficulty in effectively identifying green tides with anisotropic characteristics due to the complex and variable shapes of the patches and the wide range of scales. To address this issue, this paper presents an anisotropic green tide patch extraction network (AGE-Net) based on deformable convolution. The main structure of AGE-Net consists of stacked anisotropic feature extraction (AFEB) modules. Each AFEB module contains two branches for extracting green tide patches. The first branch consists of multiple connected dense blocks. The second branch introduces a deformable convolution module and a depth residual module based on a multiresolution feature extraction network for extracting anisotropic features of green tide patches. Finally, an irregular green tide patch feature enhancement module is used to fuse the high-level semantic features extracted from the two branches. To verify the effectiveness of the AGE-Net model, experiments were conducted on the MODIS Green Tide dataset. The results show that AGE-Net has better recognition performance, with F1-scores and IoUs reaching 0.8317 and 71.19% on multi-view test images, outperforming other comparison methods.

Two-pathway spatiotemporal representation learning for extreme water temperature prediction

Accurate predictions of extreme water temperatures are criticalto understanding the variability of the marine environment and reducing marine disasters maximized by global warming. In this study, we propose a two-pathway framework with separated spatial and temporal encoders for accurate prediction of water temperature, especially extremely high water temperature, through effective spatiotemporal representation learning. The spatial and temporal encoder networks based on the Transformer’s self-attention mechanism performs the task of predicting the water temperature time series at the 16 coastal locations around the Korean Peninsula for the seven consecutive days ahead at daily intervals with various combinations of patch embedding methods, positional embedding for spatial features. Comparative experiments with conventional deep convolutional and recurrent networks are also conducted for comparison. By comparing and assessing these results, the proposed two-pathway framework can improve the predictability of extremely high coastal water temperature by better capturing spatiotemporal interrelationships and long-range dependencies from open ocean and regional sea, and further determines the optimal architectural details of self-attention-based spatial and temporal encoders. Furthermore, to examine the explainability of the proposed model and its consistency with domain knowledge, spatial and temporal attention maps are visualized and analyzed that represents weights for spatiotemporal input sequences that are more relevant to predict for future predictions.

Quantitative assessment of personal risk during storm surge disaster

Storm surge is the most severe marine disaster in China, threatening the lives of coastal residents. Quantitative assessment of personal risk is an important prerequisite for identifying risk areas and designing emergency strategies. This paper aims to propose an economical and efficient quantitative assessment method for personal risk under storm surge disasters, including the assessment of the affected population and emergency relocation population, as well as their number and distribution. Remote Sensing products and Geographic Information System (GIS) technologies are used to form a technical framework, including the method of inundation scenario construction and personal risk assessment, which is realized by GIS spatial analysis. Based on the technical framework, the personal risk caused by “Hato” in Guangdong was assessed. The results show that the affected population is concentrated in the Pearl River Delta and dispersed in surrounding cities. The number of the affected population is assessed as 1,032,455, with an accuracy of 91.48%. The emergency relocation population is concentrated in the coastal areas of Guangzhou, Dongguan and Zhuhai, which have high population density and are far from the safety or partial safety zone. The number of the emergency relocation population is assessed as 199,973, with an accuracy of 87.25%. “Hato” verified that this method is economical, efficient, and accurate. It is expected to enrich and develop the theories and methods of personal risk assessment.

Late Holocene Climate Warming Events and Their Linkage to Hydraulic Engineering on the Coast of Hangzhou Bay, East China

The coastal lowlands in East China are very sensitive to climate change and marine disasters, and much large-scale hydraulic engineering was recorded in the historical documents of the Late Holocene. In this study, AMS 14C and OSL were used to date three sedimentary profiles from the north and south coasts of inner Hangzhou Bay, and grain size and geochemical analyses including organic carbon, macro-elements, and alkaline earth metals were performed, while hydraulic engineering records in historical documents were compiled, in an attempt to reveal the sedimentary records of extreme climatic and hydrological events over the past 3000 years and to probe into the correlation between them and hydraulic engineering. The results show that the intensified chemical weathering during ca. 200 BCE to 900 CE in East China corresponded to the warm and humid climate during the Qin-Han and Sui-Tang dynasties. Salinity intrusion with rising local water levels occurred in the lowland plains along the south coast of Hangzhou Bay from 120 to 895 CE. Low-salinity water intrusion from 32 to 488 CE was also recorded in the stratigraphy of lowland plains along the north coast of Hangzhou Bay. The sedimentary records of the East Tiaoxi River basin show river floods about 2000 years ago. The above sedimentary records indicate that the relative sea level rose in the Hangzhou Bay area during the Qin-Han and Sui-Tang Warm Periods, resulting in frequent salinity intrusion and river floods, which coincided with the historical records of hydraulic engineering such as the construction of seawalls, river levees, and the enclosure of lakes for restoration of river floods during the Han and Tang dynasties. Such coincidence reflects that climate change profoundly affected the hydrological environment of the coastal areas in East China as well as the response of the human societies.

Prospek Hubungan Maritim Indonesia – Malaysia Pasca Kesepakatan Batas Laut 2023

This article discusses the Indonesia-Malaysia maritime boundary agreement reached in 2023. This paper uses a literature review method to analyze the historical and political context that guided the maritime boundary negotiations between the two countries, particularly highlighting the role of diplomacy and foreign policy in reaching the agreement. Furthermore, it explores the legal aspects of the maritime boundary agreement and its impact on territorial claims, sovereignty and natural resource exploration rights. In the context of international relations, the article discusses how the boundary agreement may affect regional dynamics in Southeast Asia, focusing on the roles of Indonesia and Malaysia as key actors in maritime security and economic development in the region. Comparisons with similar issues in the Asia Pacific region provide a broader perspective on the global implications of this agreement. In addition, this article explores the potential for bilateral collaboration in the areas of security, fisheries surveillance and marine disaster management. Sustainable utilization of natural resources and economic development through maritime cooperation are an important focus, with an emphasis on establishing equitable and sustainable exclusive economic zones. By analyzing all these aspects, this article aims to provide a deep insight into the prospects of maritime relations between Indonesia and Malaysia post the 2023 maritime boundary agreement, as well as provide policy recommendations to strengthen the two countries' cooperation in the maritime field.

Model of Storm Surge Maximum Water Level Increase in a Coastal Area Using Ensemble Machine Learning and Explicable Algorithm

AbstractThis study proposes a novel, new ensemble model (NEM) designed to simulate the maximum water level increases caused by storm surges in a frequently cyclone‐affected coastal water of Hong Kong, China. The model relies on storm and water level data spanning 1978–2022. The NEM amalgamates three machine learning algorithms: Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and XGBoost (XGB), employing a stacking technique for integration. Six parameters, determined using the Random Forest and Recursive Feature Elimination algorithms (RF‐RFE), are used as input features for the NEM. These parameters are the nearest wind speed, gale distance, nearest air pressure, minimum distance, maximum pressure drop within 24 hr, and large wind radius. Model assessment results suggest that the NEM exhibits superior performance over RF, GBDT, and XGB, delivering high stability and precision. It reaches a coefficient of determination (R2) up to 0.95 and a mean absolute error (MAE) that fluctuates between 0.08 and 0.20 m for the test data set. An interpretability analysis conducted using the SHapley Additive exPlanations (SHAP) method shows that gale distance and nearest wind speed are the most significant features for predicting peak water level increases during storm surges. The results of this study could provide practical implications for predictive models concerning storm surges. These findings present essential tools for the mitigation of coastal disasters and the improvement of marine disaster warning systems.